A wide range of medical imaging applications benefits from the availability of realistic ground truth data. In the case of positron emission tomography (PET), ground truth data is crucial to validate processing algorithms and assessing their performances. The design of such ground truth data often relies on Monte-Carlo simulation techniques. Since the creation of a large dataset is not trivial both in terms of computing time and realism, we propose the OSSI-PET database containing 350 simulated [(11)C]Raclopride dynamic scans for rats, created specifically for the Inveon pre-clinical PET scanner. The originality of this database lies on the availability of several groups of scans with controlled biological variations in the striata. Besides, each group consists of a large number of realizations (i.e., noise replicates). We present the construction methodology of this database using rat pharmacokinetic and anatomical models. A first application using the OSSI-PET database is presented. Several commonly used reconstruction techniques were compared in terms of image quality, accuracy and variability of the activity estimates and of the computed kinetic parameters. The results showed that OP-OSEM3D iterative reconstruction method outperformed the other tested methods. Analytical methods such as FBP2D and 3DRP also produced satisfactory results. However, FORE followed by OSEM2D reconstructions should be avoided. Beyond the illustration of the potential of the database, this application will help scientists to understand the different sources of noise and bias that can occur at the different steps in the processing and will be very useful for choosing appropriate reconstruction methods and parameters.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TMI.2016.2526086 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Assessment of deep learning technique for fully automated mandibular segmentation.
Am J Orthod Dentofacial Orthop
February 2025
Department of Orthodontics, Faculty of Dentistry, Çanakkale Onsekiz Mart University, Çanakkale, Turkey.
Introduction: This study aimed to assess the precision of an open-source, clinician-trained, and user-friendly convolutional neural network-based model for automatically segmenting the mandible.
Methods: A total of 55 cone-beam computed tomography scans that met the inclusion criteria were collected and divided into test and training groups. The MONAI (Medical Open Network for Artificial Intelligence) Label active learning tool extension was used to train the automatic model.
Improving MRI turbulence quantification by addressing the measurement errors caused by the derivatives of the turbulent velocity field - Sequence development and in-vitro validation.
Magn Reson Imaging
January 2025
Institute of Fluid Mechanics, University of Rostock, Rostock, Germany.
Purpose: To improve the current method for MRI turbulence quantification which is the intravoxel phase dispersion (IVPD) method. Turbulence is commonly characterized by the Reynolds stress tensor (RST) which describes the velocity covariance matrix. A major source for systematic errors in MRI is the sequence's sensitivity to the variance of the derivatives of velocity, such as the acceleration variance, which can lead to a substantial measurement bias.
View Article and Find Full Text PDFReducing bias in source-free unsupervised domain adaptation for regression.
Neural Netw
January 2025
Luca Healthcare R&D, Shanghai, 200000, China. Electronic address:
Due to data privacy and storage concerns, Source-Free Unsupervised Domain Adaptation (SFUDA) focuses on improving an unlabelled target domain by leveraging a pre-trained source model without access to source data. While existing studies attempt to train target models by mitigating biases induced by noisy pseudo labels, they often lack theoretical guarantees for fully reducing biases and have predominantly addressed classification tasks rather than regression ones. To address these gaps, our analysis delves into the generalisation error bound of the target model, aiming to understand the intrinsic limitations of pseudo-label-based SFUDA methods.
View Article and Find Full Text PDFClimate Change-Induced Decline in Succulent in Namibia's Arid Regions.
Plants (Basel)
January 2025
Department of Plant and Soil Sciences, University of Pretoria, Hatfield, Pretoria P.O. Box X20, South Africa.
The global rise in temperatures due to climate change has made it difficult even for specialised desert-adapted plant species to survive on sandy desert soils. Two of Namibia's iconic desert-adapted plant species, and the quiver tree , have recently been shown to be under threat because of climate change. In the current study, three ecologically important Namibian milk bushes were evaluated for their climate change response.
View Article and Find Full Text PDFIncorporating Multimodal Directional Interpersonal Synchrony into Empathetic Response Generation.
Sensors (Basel)
January 2025
Faculty of Engineering, University of Toyama, Toyama 930-8555, Japan.
This study investigates how interpersonal (speaker-partner) synchrony contributes to empathetic response generation in communication scenarios. To perform this investigation, we propose a model that incorporates multimodal directional (positive and negative) interpersonal synchrony, operationalized using the cosine similarity measure, into empathetic response generation. We evaluate how incorporating specific synchrony affects the generated responses at the language and empathy levels.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!